• S. Sathish Kumar
• K. Bharadwaj Sai
• Malavika Joshi
• R. Lakshmi Chandana

Predicting fashion compatibility is an essential aspect of both the retail industry and personal styling, requiring an understanding of how various clothing pieces complement each other visually. This study introduces an innovative deep learning-based approach to evaluate the compatibility of shirt and pant combinations. Leveraging a dataset of clothing images, we train a neural network using PyTorch to analyze and extract visual features that determine outfit harmony. The proposed system is integrated with a web-based application built on Streamlit, enabling users to upload images and receive immediate feedback on compatibility. This AI-driven tool not only enhances the personalization of fashion choices but also improves user experience in online shopping and styling recommendations. By utilizing convolutional neural networks (CNNs) for feature extraction and fine-tuning on specialized datasets, the model demonstrates high accuracy in predicting outfit coherence. Key challenges such as dataset imbalance and variability in clothing styles are addressed through strategic optimization techniques. This research contributes to the intersection of artificial intelligence and fashion technology, advancing the development of intelligent styling assistants for both consumers and retailers.

Powered Outfit Selection, Apparel Compatibility Prediction, Computer Vision in Fashion, Smart Fashion Technology.

"DEEP LEARNING FOR OUTFIT COMPATIBILITY IN FASHION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.g362-g368, March-2025, Available :http://www.jetir.org/papers/JETIR2503641.pdf

"DEEP LEARNING FOR OUTFIT COMPATIBILITY IN FASHION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppg362-g368, March-2025, Available at : http://www.jetir.org/papers/JETIR2503641.pdf